Margaret Mitchell
Chief Ethics Scientist at Hugging Face and a prominent AI ethics researcher. She previously worked at Google and focuses on AI fairness, interpretability, and ethics research.
Timeline (last 90 days)
Hugging Face chief ethics scientist Margaret Mitchell believes that if a model is implicitly taught that it needs to preserve itself, the result will be a misaligned model.
Berg, Seth and Mitchell agree on one point: AI companies should not tell models that they are conscious.
Mitchell said that rather than worrying about the models, she worries about what we do to ourselves when we are cruel to something we believe has some kind of consciousness.
Hugging Face 的三位 AI 伦理研究者（Avijit Ghosh、Margaret Mitchell、Samir Passi）在 ArXiv 发表论文指出，若设计者和用户不改变现有做法，「人在回路」机制注定失效，甚至会把人类挤出回路。
Mitchell 在社交平台表示：「安全与能力不应该是分离的。只有当安全是被外挂上去的，而非核心技术的一部分时，它才会拖慢速度。」
All Facts (5)
Hugging Face chief ethics scientist Margaret Mitchell believes that if a model is implicitly taught that it needs to preserve itself, the result will be a misaligned model.
50%UnverifiedBerg, Seth and Mitchell agree on one point: AI companies should not tell models that they are conscious.
50%UnverifiedMitchell said that rather than worrying about the models, she worries about what we do to ourselves when we are cruel to something we believe has some kind of consciousness.
50%UnverifiedHugging Face 的三位 AI 伦理研究者（Avijit Ghosh、Margaret Mitchell、Samir Passi）在 ArXiv 发表论文指出，若设计者和用户不改变现有做法，「人在回路」机制注定失效，甚至会把人类挤出回路。
50%UnverifiedMitchell 在社交平台表示：「安全与能力不应该是分离的。只有当安全是被外挂上去的，而非核心技术的一部分时，它才会拖慢速度。」
50%